Schedule

• Outcome: Pass
• Latest audit: May 28, 2026, 12:29 PM
• Version:
  1.0.2

Overview

This is a transparent local scheduling skill whose main risk is that saved tasks can run later using permissions the user has granted.

Before installing, treat scheduled jobs as standing instructions. Review each job's action, timing, timezone, required skills, and whether it should expire; avoid putting secrets in task text; periodically review or delete ~/schedule/jobs.json and history logs you no longer need.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

• Confidence: 84% confidence
• Finding: The skill's simple-request patterns are broad enough that an agent may interpret underspecified natural-language requests as authorization to create or alter scheduled actions. In a scheduling context, ambiguous triggers can cause unintended persistence or execution of user-defined tasks, especially if combined with other skills or previously granted permissions.

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The skill explicitly stores job definitions, preferences, and execution history under ~/schedule/, but it does not require a user-facing disclosure that this data will persist. Retaining task descriptions, timezones, and logs can expose sensitive behavioral or operational information if the host is shared, backed up, or later accessed by another component.

VirusTotal

65/65 vendors flagged this skill as clean.